Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this is a safe, read-only, idempotent, open-world operation, and the description does add real value beyond that: public endpoint, English natural-language output, 20 items per page, and reuse of the same filters/releaseId/locale for later pages. It does not cover whether parameters are mutually exclusive, what happens with ambiguous or partial keyword matches, or any error/empty-result behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is front-loaded and dense with no filler, but several clauses are terse to the point of ambiguity ('Matches identify entries', 'without filters'), forcing the agent to infer meaning. A small amount of restructuring into search modes vs. detail mode would improve it without lengthening it much.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter, no-output-schema read tool, the description does the heavy lifting: it explains the search-vs-detail flow, the pagination contract, the return language and the fact that source documents and conditions are preserved. What is missing is the shape of a result entry and the behavior when multiple filter parameters are combined.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 75% schema coverage, the schema already documents most parameters; the description adds the relationships the schema only hints at, notably that detail requires agreementId, itemId and releaseId together and that later pages must repeat releaseId, filters and locale. Gaps remain around the 'page' parameter beyond the 20-per-page fact and around precedence when both keyword and agreementId are supplied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives specific verbs and resources: it retrieves regional occupations and conditions, finds candidate official titles via keyword, compares entries via code/officialTitle, and reads detail via agreementId/itemId/releaseId. It never differentiates itself from siblings such as get_state_dama_agreements, get_occupation_labour_agreements or search_occupations, and the opening phrase 'Regional policy directory without filters' is confusing given that keyword/code/agreementId act as filters.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly routes among parameter modes: keyword for candidate titles, code or exact officialTitle for cross-region comparison, agreementId to list or filter regional occupations, and detail mode for conditions. It stops short of stating when to use this tool instead of a sibling lookup tool or any exclusion conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.